Hough Regions for Joining Instance Localization and Segmentation

By Hayko Riemenschneider, Sabine Sternig, Michael Donoser, Peter M. Roth, Horst Bischof. 2012

31 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, neutral): “Earlier methods relied on Hough voting [36, 57].”
Monocular Object Instance Segmentation and Depth Ordering with CNNs (2015, methodology): “[30] uses Hough voting to obtain object centers and proposes a CRF model to jointly reason about the assignment of pixels to centers (which define an object instance) and predict its semantic class.”
Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs (2015, methodology): “[22] votes for object centers and uses a MRF to infer the assignment of pixels to object centers.”
segmentation in plant phenotyping: a collation study. Machine Vision and Applications (2017, background): “Another interesting work [47] relies on Hough voting to jointly detect and segment objects.”
Learning to Detect Partially Overlapping Instances (2013, background): “Thus rather than trying to reason about the boundary and part assignment between several tightly overlapping regions [3, 8, 14, 21], tuples of objects are detected as a whole, making the object detection process more resilient to strong object overlap.”
SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation – A Synthetic Dataset and Baselines (2019, background): “A variety of other techniques based on voting, reﬁnement, multi-task learning and grouping, e.g ., [8, 84, 55, 99, 77, 78, 21, 22, 64], have been investigated.”
Detecting Partially Occluded Objects with an Implicit Shape Model Random Field (2012, methodology): “We use the extended ground truth from [15].”
Instance-Level Segmentation with Deep Densely Connected MRFs (2015, background): “A mask is in many ways richer than a box: it allows an informed reasoning about occlusion and depth layering.”
Learning Instance Occlusion for Panoptic Segmentation (2019, background): “Instance segmentation [27, 28, 5, 20, 10, 29, 39, 15] requires the detection and segmentation of each thing (countable object instance) within an image, while semantic segmentation [30, 34, 9, 24, 2, 41, 40] provides a dense perpixel classification without distinction between instances within the sa”